<title>Segmentation of medical images using adaptive region growing</title>

Abstract

Interaction increases flexibility of segmentation but it leads to undesirable behavior of an algorithm if knowledge being requested is inappropriate. In region growing, this is the case for defining the homogeneity criterion, as its specification depends also on image formation properties that are not known to the user. We developed a region growing algorithm that learns its homogeneity criterion automatically from characteristics of the region to be segmented. The method is based on a model that describes homogeneity and simple shape properties of the region. Parameters of the homogeneity criterion are estimated from sample locations in the region. These locations are selected sequentially in a random walk starting at the seed point, and the homogeneity criterion is updated continuously. This approach was extended to a fully automatic and complete segmentation method by using the pixels with the smallest gradient length in the not yet segmented image region as a seed point. The methods were tested for segmentation on test images and of structures in CT and MR images. We found the methods to work reliable if the model assumption on homogeneity and region characteristics are true. Furthermore, the model is simple but robust, thus allowing for a certain degree of deviation from model constraints and still delivering the expected segmentation result.

A Review on the Current Segmentation Algorithms for Medical Images

“…To eliminate the dependence on initial seeds and make the algorithm automatically, statistical information and a priori knowledge can be incorporated to the algorithms. For example, a homogeneity criterion was introduced in (Pohle and Toennies, 2001) which made the region growing algorithms adaptive for the different locations of initial seeds and achieved success in the segmentation of CT and MR images. However, as the algorithms mainly rely on the image intensity information, they are hard to handle the partial volume effects and control the leakage.…”

A Hybrid Approach to Brain Extraction from Premature Infant MRI

“…Pohle et al [14] proposed an adaptive region growing to segment regions in medical images using two runs of the region growing. However, if conditions such as shape differences or intensity changes within the region of interest are not well defined then the method does not work well.…”

Automatic Detection for Healthy and Unhealthy Kidneys on Abdominal CT Images using Machine Learning Algorithm

“…Pohle and Toennies developed a regiongrowing algorithm that automatically learns its homogeneity criterion from the characteristics of the region that is segmented [2][3][4]. This approach is less sensitive to the seed point location.…”